检索结果-内蒙古大学图书馆

Hyper Spectral Spatial Image Segmentation Using Machine Learning Algorithms 1

Hyper Spectral Spatial Image Segmentation Using Machine Lear...

1st International Conference on Intelligent Technologies for Sustainable Electric and Communications systems, iTech SECOM 2023

作者： Saravanan, G. Suresh, A. Jagannathan, J. Thanga Mariappan, L. Majeeth, Najeem Dheen Abdul Kumar, Nithish Veltech Rangarajan Dr.Sagunthala R and D Institute of Science and Technology Department of Computer Science and Engineering Tamilnadu India Vellore Institute of Technology School of Computer Science and Engineering Tamilnadu Vellore India Vellore Institute of Technology School of Computer Science Engineering and Information Systems Tamilnadu Vellore India Saveetha Engineering College Department of Artificial Intelligence and Machine Learning Tamilnadu India

ISBN: (纸本)9798350371185

In recent years, there has been a notable surge in the development of methods dedicated to classifying hyper spectral image samples. However, the inherent high dimensionality of hyper spectral data presents significant challenges for traditional supervised classification algorithms. Prior studies have attempted to address these challenges by incorporating active learning methods for hyper spectral data segmentation. Nevertheless, a crucial drawback of active learning lies in its dependence on labeled data samples, leading to less improved classification results for unlabeled data samples. In response to this limitation, our work introduces Supervised Active Learning (SAL) techniques that harness both spectral and spatial information. The key innovation of our research lies in the introduction of a novel hyper spectral image segmentation approach based on the k-dependence Bayesian (KDB) model. We estimate the maximizer of the posterior marginal using Symmetric Iterative Proportional Fitting (SIPF) within this KDB model. By implementing the KDB model for hyper spectral image segmentation, our goal is to enhance the classification accuracy of our SAL classifiers. The SAL framework integrates shape prior probability estimation, class density results from Improved Multi-Level Logistic (IMLL) methods, and the maximization of the posterior marginal estimated through Symmetric Iterative Proportional Fitting (SIPF). We evaluate the accuracy of our proposed MPM-SIPF-SAL system using the real ROSIS Hyper Spectral Dataset, demonstrating that our system outperforms existing methods in terms of classification accuracy. © 2023 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

5-bit all free space optical quantum random number generator 10

5-bit all free space optical quantum random number generator

引用

Quantum and Nonlinear Optics X 2023

作者： Li, Shaojie Fan, Jintao Zhu, Xiaoxuan Lu, Yang Hu, Minglie Ultrafast Laser Laboratory Key Laboratory of Opto-electronic Information Science and Technology of Ministry of Education School of Precision Instruments and Opto-electronics Engineering Tianjin University Tianjin300072 China

ISBN: (纸本)9781510667990

Random numbers play an important role in many fields, such as computation, simulation and cryptography. The randomness inherent in quantum mechanics is a perfect source of entropy for a true random number generator. Nevertheless, many QRNG schemes require post-processing work to ensure randomness. On the other hand, the bit number of the QRNG is limited, which hamper its further applications. Here, we demonstrate a novel 5-bit all free space optical quantum random number generator based on a time-division-multiplexed degenerate optical parametric oscillator (DOPO), which does not need a complicated experimental environment and tedious post-processing work. By inserting a multi-pass cell into the optical parametric oscillator, the equivalent cavity length is calculated to be as long as 15 m, which corresponds to fifth of the separation times of pump pulses. As a result, 5 identical DOPO pulses are generated simultaneously. The randomness comes from phase responses of degenerate OPOs. Under threshold, the photons produced by optical parametric down conversion have random initial phase, while above threshold, stable oscillations occurs in one of the two possible phase states. Random number is reliably verified by measuring the relative phase states between DOPO output pulses and the original pump pulse using a fast response photodiode. All spatial structures have the advantages of higher stability and are less sensitive to temperature fluctuation. The bit number can be readily multiplied by increasing the cavity length of DOPO or the repetition rate of the pump laser source. © 2023 SPIE.

关键词： Nonlinear optics

来源：评论

学校读者我要写书评

暂无评论

Optical scrambler using WGM micro-bottle cavity

引用

Chinese Optics Letters 2023年第6期21卷 6-10页

作者：常朋发王晨蒋涛王龙生赵彤高华贾志伟郭园园王云才王安帮 Key Laboratory of Advanced Transducers&Intelligent Control Systems Ministry of Education and Shanxi ProvinceCollege of Physics&Optoelectronic EngineeringTaiyuan University of TechnologyTaiyuan 030024China Guangdong Provincial Key Laboratory of Photonics Information Technology School of Information EngineeringGuangdong University of TechnologyGuangzhou 510006China

An optical scrambler using a whispering-gallery-mode[WGM]micro-bottle cavity to scramble a complex optical signal to generate an uncorrelated output is *** experimentally demonstrated this micro-cavity scrambler by using chaotic laser light as the incident signal and studied the influence of the coupling *** achieved full scrambling with a low cross correlation of 0.028 between the output and the *** indicate that the scrambling effect originates from the interference among numerous WGMs in the bottle *** is believed that the micro-bottle cavity with an efficient scrambling function can become a promising candidate for encryption.

关键词： scrambler encryption whispering gallery mode micro-bottle cavity secure communication

来源：评论

学校读者我要写书评

暂无评论

A Facial Expression Recognition Method based on Residual Separable Convolutional Neural Network

Journal of Network Intelligence

引用

Journal of Network Intelligence 2022年第1期7卷 59-69页

作者： Xu, Xiaoyu Cui, Jianfeng Chen, Xuhui Chen, Chin-Ling College of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China College of Software Engineering Xiamen University of Technology Xiamen361024 China Fujian Key Laboratory of Internet of things application technology Xiamen361024 China Xiamen City University of Technology Xiamen361024 China School of Computer and Information Engineering Xiamen City University of Technology Xiamen361024 China School of Information Engineering Changchun Sci-Tech University Changchun130600 China Department of Computer Science and Information Engineering Chaoyang University of Technology Taichung41349 Taiwan

Facial expression recognition is a typical application of artificial intelligence. It has practical value and commercial prospects in application scenarios such as safe driving, medical assistance, online classrooms, and human-computer interaction. Traditional convolutional neural networks have low accuracy in facial expression recognition. To solve this problem, we propose a residual separable convolutional neural network, which combines depth-wise separable convolution with an improved residual network. When transmitting feature information, it fuses facial expression features through skip connection and utilizes global average pooling to reduce dimension, thus preventing gradient disappearance. We conduct experiments based on the data set FER2013. The results show that it can improve the accuracy of facial expression recognition, reduce model parameters and raise the utilization efficiency of the parameters effectively. © The Authors.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Ultraviolet spatiotemporal optical vortices via sum-frequency generation

Ultraviolet spatiotemporal optical vortices via sum-frequenc...

引用

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Fan, Jintao Wang, Jue Gao, Xuechen Lu, Yang Zhao, Yuwei Zhang, Jiaxuan Hu, Minglie Ultrafast Laser Laboratory Key Laboratory of Opto-Electronic Information Science and Technology of Ministry of Education College of Precision Instruments and Opto-Electronics Engineering Tianjin University Tianjin300072 China

ISBN: (纸本)9781957171258

关键词： Interferometry

来源：评论

学校读者我要写书评

暂无评论

Symmetry breaking of highly symmetrical nanoclusters for triggering highly optical activity

引用

Fundamental Research 2024年第1期4卷 63-68页

作者： Xiao Wei Hao Li Honglei Shen Chuanjun Zhou Shuxin Wang Xi Kang Manzhou Zhu Department of Chemistry and Centre for Atomic Engineering of Advanced Materials Key Laboratory of Structure and Functional Regulation of Hybrid Materials of Ministry of EducationInstitutes of Physical Science and Information Technology and Anhui Province Key Laboratory of Chemistry for Inorganic/Organic Hybrid Functionalized Materials.Anhui UniversityHefei 230601China

Developing new approaches to fulfill the enantioseparation of nanocluster racemates and construct cluster-based nanomaterials with optical activity remains highly desired in cluster science,because it is an essential prerequisite for fundamental research and extensive applications of these *** herein propose a strategy termed“active-site exposing and partly re-protecting”to trigger the symmetry breaking of highly symmetrical nanoclusters and to render cluster crystals optically *** vertex PPh_(3)of the symmetrical Ag_(29)(SSR)_(12)(PPh_(3))_(4)(SSR=1,3-benzenedithiol)nanocluster was firstly dissociated in the presence of counterions with large steric hindrance,and then the exposed Ag active sites of the obtained Ag_(29)(SSR)_(12)nanocluster were partly re-protected by Ag^(+),yielding an Ag_(29)(SSR)_(12)-Ag_(2)nanocluster with a symmetry-breaking ***_(29)(SSR)_(12)-Ag_(2)followed a chiral crystallization mode,and its crystal displayed strong optical activity,derived from CD and CPL ***,this work presents a new approach(i.e.,active-site exposing and partly re-protecting)for the symmetry breaking of highly symmetrical nanoclusters,the enantioseparation of nanocluster racemates,and the achievement of highly optical activity.

关键词： Atomically precise nanocluster Symmetry breaking Enantioseparation Circularly polarized luminescent Photoluminescence

来源：评论

学校读者我要写书评

暂无评论

The triggering of catalysis via structural engineering at atomic level: Direct propane dehydrogenation on Fe-N_(3)P-C

引用

Chinese Chemical Letters 2023年第3期34卷 442-446页

作者： Wenyi Bian Xueli Shen Huang Tan Xing Fan Yunxia Liu Haiping Lin Youyong Li Institute of Functional Nano&Soft Materials(FUNSOM) Jiangsu Key Laboratory for Carbon-Based Functional Materials&DevicesSoochow UniversitySuzhou 215123China School of Physics and Information Technology Shaanxi Normal UniversityXi’an 710062China Macao Institute of Materials Science and Engineering Macao University of Science and TechnologyMacaoChina

The on-purpose direct propane dehydrogenation(PDH) has received extensive attention to meet the everincreasing demand of *** this work,by means of density functional theory(DFT) calculations,we systematically studied the intrinsic coordinating effect of Fe single-atom catalysts in ***,the N and P dual-coordinated single Fe(Fe-N_(3)P-C) significantly outperform the Fe-N_(4-)C site in catalysis and exhibit desired activity and selectivity at industrial PDH *** mechanistic origin of different performance on Fe-N_(3)P-C and Fe-N_(4-)C has been ascribed to the geometric *** be specific,the in-plane configuration of Fe-N_(4) site exhibits low H affinity,which results in poor activity in C-H bond *** contrast,the out-of-plane structure of Fe-N_(3)P-C site exhibits moderate H affinity,which not only promote the C-H bond scission but also offer a platform for obtaining appropriate H diffusion rate which ensures the high selectivity of propylene and the regeneration of *** work demonstrates promising applications of dual-coordinated single-atom catalysts for highly selective propane dehydrogenation.

关键词： Non-oxidative propane dehydrogenation Propylene selectivity Single-atom catalysis Heteroatom-doped graphene Fe catalyst

来源：评论

学校读者我要写书评

暂无评论

A Simulation Assessment Method of Phased-Mission Reliability Considering Maintenance 12

A Simulation Assessment Method of Phased-Mission Reliability...

引用

12th International Conference on Quality, Reliability, Risk, Maintenance, and Safety engineering, QR2MSE 2022

作者： Zhu, He-Xuan Yuan, Hong-Jie Zeng, Sheng-Kui School of Reliability and Systems Engineering Science and Technology on Reliability and Environment Engineering Laboratory Beihang University Beijing100191 China

ISBN: (纸本)9781839538360

Considering the characteristics of muti-phased mission and repair of warship system, there are difficulties in the application of traditional solution methods to model and evaluate the system reliability. A simulation strategy combined with the state transition algorithm based on Monte Carlo method is proposed to calculate ship mission reliability. The mission reliability simulation is demonstrated with three examples and a complex warship system to verify the feasibility and accuracy of the method. The results suggest that the simulation model built in this paper is credible and has certain guiding significance for the design and improvement of warship task allocation. © 2022 IEEE.

关键词： Warships

来源：评论

学校读者我要写书评

暂无评论

Broadband THz Edge-Enhanced Imaging technology Based on Electro-Optic Sampling 2

Broadband THz Edge-Enhanced Imaging Technology Based on Elec...

引用

2nd International Conference on Electronic information and Communication engineering, EICE 2023

作者： Yuan, Xingming Li, Ying Lin, Qinggang Chen, Jiapin Cai, Yi Xu, Shixiang Li, Jingzhen Shenzhen Key Laboratory of Micro-Nano Photonic Information Technology Key Laboratory of Optoelectronic Devices and Systems Ministry of Education and Guangdong Province College of Physics and Optoelectronic Engineering Shenzhen University Guangdong518060 China SZU-NUS Collaborative Innovation Center for Optoelectronic Science & Technology Key Laboratory of Optoelectronic Devices and Systems Ministry of Education and Guangdong Province Shenzhen University Guangdong518060 China

Based on the radial Hilbert transform of spatial filtering and electro-optical sampling, we propose a broadband terahertz edge-enhanced imaging method in this work. Instead of using a narrow-band THz vortex phase plate, here we use vortex ultrashort laser pulse to realize the THz enhancement imaging which can be applied for few-cycle THz imaging. The principle of edge enhancement is analyzed theoretically, and the analytical expression of the final terahertz imaging is derived. We found that edge-enhancement imaging corresponds to the nonlinear term of the THz field, and the background and linear terms can be suppressed when the static birefringent phase is set to zero. The simulations show that our method can effectively improve the contrast and signal-to-noise ratio of terahertz imaging. © Published under licence by IOP Publishing Ltd.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Effectiveness of Using Deep Learning for Blister Blight Identification in Sri Lankan Tea

Effectiveness of Using Deep Learning for Blister Blight Iden...

引用

2023 International Research Conference on Smart Computing and systems engineering, SCSE 2023

作者： Hewawitharana, G.H.A.U. Nawarathne, U.M.L.A. Hassan, A.S.F. Wijerathna, Lochana M. Sinniah, G.D. Vidhanaarachchi, Samitha P. Wickramarathne, Jagath Wijekoon, Janaka L. Sri Lanka Institute of Information Technology Department of Information Technology Malabe Sri Lanka Tea Research Institute of Sri Lanka Plant Pathology Division Talawakelle Sri Lanka Sri Lanka Institute of Information Technology Department of Computer Science and Software Engineering Malabe Sri Lanka Military Technological College Systems Engineering Department Muscat Oman

ISBN: (纸本)9798350341454

Ceylon tea industry faces a major challenge in the form of pathogen-induced crop loss, with Blister Blight (BB) caused by Exobasidium vexans posing the greatest threat, leading to harvest losses of over 30%. This fungus attacks the tender tea shoots, resulting in a direct negative impact on the tea harvest. This paper presents a system to identify the suspicious tea leaves and BB disease at its early stages along with an assessment of severity, offering a potential solution to this critical issue. By utilizing real-time object detection, the system filters out non-tea leaves from the captured initial image of a segment of a tea plant. The identified tea leaves are then subjected to BB identification and severity assessment based on differing visual symptoms of the BB stages. This approach enables the system to accurately identify BB in the initial stage and severity stage, allowing for timely and targeted intervention to minimize crop losses. The YOLOv8 model has been able to correctly identify 98% of the objects it has detected as relevant (precision), and it has been able to correctly identify 96% of all the relevant objects present in the scene (recall). The Residual Network 50 (Resnet50) convolutional neural network (CNN) model was selected as the final model, achieving an accuracy of 89.90% during the training phase and an accuracy of 88.26% during the testing phase. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：